Dataset Information

Rapid identification of slow healing wounds.

ABSTRACT: Chronic nonhealing wounds have a prevalence of 2% in the United States, and cost an estimated $50 billion annually. Accurate stratification of wounds for risk of slow healing may help guide treatment and referral decisions. We have applied modern machine learning methods and feature engineering to develop a predictive model for delayed wound healing that uses information collected during routine care in outpatient wound care centers. Patient and wound data was collected at 68 outpatient wound care centers operated by Healogics Inc. in 26 states between 2009 and 2013. The dataset included basic demographic information on 59,953 patients, as well as both quantitative and categorical information on 180,696 wounds. Wounds were split into training and test sets by randomly assigning patients to training and test sets. Wounds were considered delayed with respect to healing time if they took more than 15 weeks to heal after presentation at a wound care center. Eleven percent of wounds in this dataset met this criterion. Prognostic models were developed on training data available in the first week of care to predict delayed healing wounds. A held out subset of the training set was used for model selection, and the final model was evaluated on the test set to evaluate discriminative power and calibration. The model achieved an area under the curve of 0.842 (95% confidence interval 0.834-0.847) for the delayed healing outcome and a Brier reliability score of 0.00018. Early, accurate prediction of delayed healing wounds can improve patient care by allowing clinicians to increase the aggressiveness of intervention in patients most at risk.

SUBMITTER: Jung K

PROVIDER: S-EPMC4820011 | biostudies-literature | 2016 Jan-Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Rapid identification of slow healing wounds.

Jung Kenneth K Covington Scott S Sen Chandan K CK Januszyk Michael M Kirsner Robert S RS Gurtner Geoffrey C GC Shah Nigam H NH

Wound repair and regeneration : official publication of the Wound Healing Society [and] the European Tissue Repair Society 20160101 1

Chronic nonhealing wounds have a prevalence of 2% in the United States, and cost an estimated $50 billion annually. Accurate stratification of wounds for risk of slow healing may help guide treatment and referral decisions. We have applied modern machine learning methods and feature engineering to develop a predictive model for delayed wound healing that uses information collected during routine care in outpatient wound care centers. Patient and wound data was collected at 68 outpatient wound ca ...[more]

PMID: 26606167

Similar Datasets

Project description:BackgroundAdult mammalian tissues heal injury to the skin with formation of scar; this process quickly seals an injured area, however, excessive scar formation can become a source of persistent pathology, interfering with multiple vital functions. In contrast, mammalian fetal tissue can heal without scar formation. We previously sought to model scarless healing in a rabbit fetal skin wound and identified gene products differentially expressed during fetal wound healing through PCR suppression subtractive hybridization (PCR SSH). One of these transcripts, previously identified simply as clone 11, showed putative increased expression in wounded fetal skin. This study establishes its identity as Ero1L-alpha and confirms its elevated expression in healing fetal wounds.FindingsAfter obtaining further sequence by 5' rapid amplification of cloned ends (RACE) we find that clone 11 is Ero1L-alpha. We determined that clone 11, a differentially expressed transcript in fetal wound healing, comprises the 3' untranslated region (UTR) of an approximately 4 kb transcript in rabbit tissues that corresponds to Ero1L-alpha. We showed that Ero1L-alpha is expressed predominantly as two transcripts in rabbit skin, namely a 1.6 kb transcript and the 4.0 kb transcript recovered in our PCR SSH screen via its 3' UTR sequence. However, a third transcript of 2.9 kb was also detected in Northern blots and was subsequently cloned and confirmed by 3' RACE. Knockdown of the clone 11 sequence in rabbit adult fibroblasts via siRNA resulted in significantly decreased Ero1L-alpha message expression. Increased expression of clone 11 (Ero1L-alpha) in a variety of cell types during the wound healing response was also confirmed by in situ hybridization.ConclusionsEro1L-alpha is one of the previously unknown clones identified in a PCR SSH screen for genes differentially expressed in fetal wounded tissue. In situ hybridization confirms that Ero1L-alpha shows increased expression in multiple cell types after wounding of the fetal integument.

Dataset Information

Rapid identification of slow healing wounds.

Publications

Rapid identification of slow healing wounds.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets